cbeta 3.6.16 → 3.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 54335ea806bf1c208341687f6028b43919452a9227cc72702dc2e3c39bcc0930
-  data.tar.gz: de5b6004c9313c55b8cc4b0bf9bbf04a8dffdadf2dcf12a850b26e12fe0e6132
+  metadata.gz: 02f6421948b47e5d049f7e5a695b5c7b4b73519401e6bd13a24ba4e96b685eb3
+  data.tar.gz: 8f8bcd8c63d9dbc3b54aa9dfdd841b95b8819776c2a185ff04dee106ee3f538a
 SHA512:
-  metadata.gz: 9bd998e632c0e2124d9c068ecb2abbe799a4545c36e242410ccb8ae7ccaf4736724508cbcfc51705427deeb413603f3600c324120798e326ee93f5718158960f
-  data.tar.gz: 955c2c07ad20786dd38c974ffcec17b0a27391a086f7d6556ec99f493a4f2b9569d47f2b211573776e885d396d45f98ab12dba661bee868fdd8462e07dbf9eae
+  metadata.gz: dbb2320988bcccc49f6daf616a78ff7e64bffcb94fe989d6c68955952dce891bf79ec580e7911a0099b343c0aaf675b5f6cde189dc344a734a5848b46a4101d5
+  data.tar.gz: 6dd81d74d311de2e7339fa045a9a2e78b94710a47e2eb9e9ebe0108611401ce51c02d1dabe27b31fd0c6488ed0e2d3527311df0de5ceff64fba479ad7cb65c24

data/lib/cbeta/p5a_checker.rb

@@ -17,6 +17,7 @@ require_relative 'cbeta_share'
 #   * [E12] note 直接出現在 lg 下
 #   * [E13] tt 直接出現在 lg 下
 #   * [E14] <anchor type="right"> 不應直接出現在 div 或 body 下
+#   * [E15] <note> corresp 無對應的 <note>
 #
 # * 警告類型
 #   * [W01] 夾注包夾注
@@ -33,7 +34,7 @@ class CBETA::P5aChecker
     @xml_root = xml_root
     @figures = figures
     @log = log
-    @errors = ''
+    @errors = []
     @g_errors = {}
   end
   
@@ -118,17 +119,17 @@ class CBETA::P5aChecker
   def display_errors
     @g_errors.keys.sort.each do |k|
       s = @g_errors[k].to_a.join(',')
-      @errors << "#{k} 無缺字資料，出現於：#{s}\n"
+      @errors << "#{k} 無缺字資料，出現於：#{s}"
     end
     
     if @errors.empty?
       puts "檢查完成，未發現錯誤。"
     elsif @log.nil?
-      puts "發現錯誤："
-      puts @errors
+      puts "發現 #{@errors.size} 錯誤："
+      puts @errors.join("\n")
     else
-      File.write(@log, @errors)
-      puts "發現錯誤，請查看 #{@log}"
+      File.write(@log, @errors.join("\n"))
+      puts "發現 #{@errors.size} 錯誤，請查看 #{@log}"
     end
   end
 
@@ -197,13 +198,9 @@ class CBETA::P5aChecker
   end
 
   def e_note(e)
-    if e.parent.name == 'div'
-      error "[E11] note 直接出現在 div 下"
-    end
-    
-    if e.parent.name == 'lg'
-      error "[E12] note 直接出現在 lg 下"
-    end
+    error "[E11] note 直接出現在 div 下" if e.parent.name == 'div'    
+    error "[E12] note 直接出現在 lg 下" if e.parent.name == 'lg'
+    e_note_corresp(e) if e.key?('corresp')
 
     unless e['place'] == 'inline'
       traverse(e)
@@ -213,11 +210,18 @@ class CBETA::P5aChecker
     if @element_stack.include?('inline_note')
       error "[W01] 夾注包夾注"
     end
+
     @element_stack << 'inline_note'
     traverse(e)
     @element_stack.pop
   end
 
+  def e_note_corresp(e)
+    n = e['corresp'].delete_prefix('#')
+    return if @notes.include?(n)
+    error "[E15] note corresp #{n} 無對應 note"
+  end
+
   def e_p(e)
     if e.parent.name == 'list'
       error "[E10] p 不應直接出現在 list 下"
@@ -261,8 +265,8 @@ class CBETA::P5aChecker
   end
 
   def error(msg)
-    s = "#{msg}, #{@basename}, lb: #{@lb}\n"
-    print s
+    s = "#{msg}, #{@basename}, lb: #{@lb}"
+    puts "\n#{s}"
     @errors << s
   end
   
@@ -281,7 +285,7 @@ class CBETA::P5aChecker
 
     s = File.read(fn)
     if s.include? "\u200B"
-      @errors << "#{@basename} 含有 U+200B Zero Width Space 字元\n"
+      @errors << "#{@basename} 含有 U+200B Zero Width Space 字元"
     end
     
     doc = Nokogiri::XML(s)
@@ -292,7 +296,7 @@ class CBETA::P5aChecker
       @element_stack = []
       traverse(doc.root)
     else
-      @errors << "錯誤: #{@basename} not well-formed\n"
+      @errors << "錯誤: #{@basename} not well-formed"
     end
   end
 
@@ -315,7 +319,7 @@ class CBETA::P5aChecker
   end
   
   def handle_vol(folder)
-    puts "check vol: #{File.basename(folder)}"
+    print "\rcheck vol: #{File.basename(folder)}  "
     Dir.entries(folder).sort.each do |f|
       next if f.start_with? '.'
       path = File.join(folder, f)

data/lib/cbeta.rb

@@ -12,6 +12,16 @@ class CBETA
   DATA = File.join(File.dirname(__FILE__), 'data')
   PUNCS = ',.()[] 。‧．，、；？！：︰／（）「」『』《》＜＞〈〉〔〕［］【】〖〗〃…—─　～│┬▆△＊＋－＝'
   
+  # 經號 (不含 Canon ID):
+  #   四碼數字 T0001
+  #   四碼數字 + 英文字母 T0150A, T0128a
+  #   英文字母 + 三碼數字 JA041, ZWa073
+  WORK_PART = '\d{4}[a-zA-Z]?|[ABa]\d{3}'
+
+  # XML file 主檔名
+  # GA010n0009
+  BASENAME = "(?:#{CANON})\\d{2,3}n(?:#{WORK_PART})"
+  
   # 由 行首資訊 取得 藏經 ID
   # @param linehead[String] 行首資訊, 例如 "T01n0001_p0001a01" 或 "GA009n0008_p0003a01"
   # @return [String] 藏經 ID，例如 "T" 或 "GA"
@@ -37,6 +47,8 @@ class CBETA
   # @param lb[String] 例如 "0001a01" 或 "0757b29"
   # @return [String] CBETA 行首資訊，例如 "T01n0001_p0001a01" 或 "T25n1510ap0757b29"
   def self.get_linehead(file_basename, lb)
+    return nil if file_basename.nil?
+    
     if file_basename.match(/^(T\d\dn0220)/)
       r = $1
     else
@@ -46,6 +58,22 @@ class CBETA
     r += 'p' + lb
     r
   end
+
+  # 由 XML檔主檔名 取得 典籍編號
+  # @param fn[String] 檔名, 例如 "T01n0001" 或 "GA009n0008"
+  # @return [String] 典籍編號，例如 "T0001" 或 "GA0008"
+  def self.get_work_id_from_file_basename(fn)
+    r = fn.sub(/^(#{CANON})\d{2,3}n(.*)$/, '\1\2')
+    r = 'T0220' if r.start_with? 'T0220'
+    r
+  end
+
+  # 由 行首資訊 取得 典籍編號
+  # @param linehead[String] CBETA 行首資訊，例如 "T01n0001_p0001a01" 或 "T25n1510ap0757b29"
+  # @return [String] 典籍編號，例如 "T0001" 或 "T1510a"
+  def self.get_work_id_from_linehead(linehead)
+    linehead.sub(/^(#{CANON})\d{2,3}n(#{WORK_PART}).*$/, '\1\2')
+  end
   
   # 由 冊號 及 典籍編號 取得 XML 主檔名
   # @param vol[String] 冊號, 例如 "T01" 或 "GA009"
@@ -114,24 +142,13 @@ class CBETA
   #   ex: J36nB348_p0284c01
   # @return [String] XML檔相對路徑，例如 "GA/GA009/GA009n0008.xml"
   def self.linehead_to_xml_file_path(linehead)
-    # 經號: 四碼數字 + 英文字母 或如 嘉興藏 英文字母 + 三碼數字
-    w = '(?:\d+[a-zA-Z]?|[AB]\d{3})'
-    if m = linehead.match(/^(?<work>(?<vol>(?<canon>#{CANON})\d+)n#{w}).*$/)
+    if m = linehead.match(/^(?<work>(?<vol>(?<canon>#{CANON})\d+)n(?:#{WORK_PART})).*$/)
       File.join(m[:canon], m[:vol], m[:work]+'.xml')
     else
       nil
     end
-  end
-  
-  # 由 XML檔主檔名 取得 典籍編號
-  # @param fn[String] 檔名, 例如 "T01n0001" 或 "GA009n0008"
-  # @return [String] 典籍編號，例如 "T0001" 或 "GA0008"
-  def self.get_work_id_from_file_basename(fn)
-    r = fn.sub(/^(#{CANON})\d{2,3}n(.*)$/, '\1\2')
-    r = 'T0220' if r.start_with? 'T0220'
-    r
-  end
-  
+  end  
+
   # 由「藏經 ID」取得「排序用編號」，例如：傳入 "T" 回傳 "A"；傳入 "X" 回傳 "B"
   # @param canon [String] 藏經 ID
   # @return [String] 排序用編號

metadata

@@ -1,13 +1,40 @@
 --- !ruby/object:Gem::Specification
 name: cbeta
 version: !ruby/object:Gem::Version
-  version: 3.6.16
+  version: 3.7.1
 platform: ruby
 authors:
 - Ray Chou
 bindir: bin
-cert_chain: []
-date: 2025-07-29 00:00:00.000000000 Z
+cert_chain:
+- |
+  -----BEGIN CERTIFICATE-----
+  MIIEaDCCAtCgAwIBAgIBATANBgkqhkiG9w0BAQsFADA9MQ8wDQYDVQQDDAZ6aG91
+  YngxFTATBgoJkiaJk/IsZAEZFgVnbWFpbDETMBEGCgmSJomT8ixkARkWA2NvbTAe
+  Fw0yNTEwMTMwNjM4MjdaFw0yNjEwMTMwNjM4MjdaMD0xDzANBgNVBAMMBnpob3Vi
+  eDEVMBMGCgmSJomT8ixkARkWBWdtYWlsMRMwEQYKCZImiZPyLGQBGRYDY29tMIIB
+  ojANBgkqhkiG9w0BAQEFAAOCAY8AMIIBigKCAYEAiyVQ5WW6oy4b8drYYebSMVi+
+  EC1xHNgAuTmlKF0w/Z2mRwL7rTOt/d3zUpTGRwBiqz3JF4ZAJksei6y7UzbA4qDb
+  WZDv+s6y6SZfeB+1JLDQOGJ+XxiM6ezsgMyZIeAOXciELTJh/x/R6pRatVDPyOAB
+  E1uv/2qGTP8Vy76fH0N9E5WU7xccPWR9uFlPKcpiAS1werNVS8/UCSyeS90o5ckE
+  rp5jOTpy7Dtzlz82qMDFGFaLh1Zo7SYeNEJlroZYec9vdnYUWmyT52l12IH6uFll
+  DvnhRkwVIdQ9l2as1PQx9eg69Jf9qSCAuOXMVojNkwWLsezyjB5CcidL8wx8Sifg
+  mKWoeNrWYbwH1h9B1dzX2jIwqcr8BNI2usK42YWyxiJGbQr+SBHhXEt25s3AVH+P
+  YUby2af2Gcb5ltpqqdXFoO8PpDODWtUcHM3NTL2uGbKvq1Ai0GhPJNHPco2SW9DA
+  AGQFSEgJj7BlHDHcYpOXfsuQxnKXeeCw6dVmyYfPAgMBAAGjczBxMAkGA1UdEwQC
+  MAAwCwYDVR0PBAQDAgSwMB0GA1UdDgQWBBTqBx17iPvliZ0RKL1RZluB50Uc/jAb
+  BgNVHREEFDASgRB6aG91YnhAZ21haWwuY29tMBsGA1UdEgQUMBKBEHpob3VieEBn
+  bWFpbC5jb20wDQYJKoZIhvcNAQELBQADggGBAF+XmQPhEcuiRl/Zb+1vIBnR8Z8Q
+  mTJm4inGy8boLAz71Pg04yI+moj7A0CSS/xbv1MtZqOzTxGFm16xLczY4k6BuRof
+  C9usw3Z7val3rHRzmdhLqkX4ALrLzd/G0uirARIQ08N5r0ETIkNFCdePtRHH8uk3
+  Er0v4v4QT9ATyrAs4iImWlhmWZIEXOdhBqW01c9/cm5Gcg/WBjdEplpJtGGnMkdc
+  zQQscleWWbCX7QKjR9rSCPNteUuzAoS8gNCbLNQF88aOFzm704dePli3WNL/GTvy
+  frO5NqUXpwCOzgCbMKfxYBw87WDA8yAE2Cn3Kw1bvX/fheUNr++QyVY8sqVDOlUC
+  TovfZCtNma/D0DD8q8enl7UEwKWEs3IC+8bu6jlzYn/6BcLTkKwzB8NXSLVGkFva
+  xyQse8slbARanDyyT6HCYtlaKD9WYw647tkJhyY2GniloCNcOJS0URvhlulLzJYg
+  9CrAxVAO2NMeM6tbxg1VjYbqopjoLCwLdAJouA==
+  -----END CERTIFICATE-----
+date: 2025-11-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unihan2
@@ -118,7 +145,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.9
+rubygems_version: 3.7.2
 specification_version: 4
 summary: CBETA Tools
 test_files: []